© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 104492
    Prev
    Next
    INDEX
    Explanations

    instances of the term "og" and related content about social media and modern communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moran
    -0.07
    JKLMNOP
    -0.06
    ington
    -0.06
     Prosper
    -0.06
     wy
    -0.06
     Wikip
    -0.06
     Hunter
    -0.06
     Gim
    -0.06
    TURE
    -0.06
     Meng
    -0.06
    POSITIVE LOGITS
    :title
    0.08
    .scalablytyped
    0.07
    dyn
    0.07
    spender
    0.07
    title
    0.07
     дÑĢÑĥж
    0.06
    elu
    0.06
     Rel
    0.06
    :description
    0.06
    سد
    0.06
    Activations Density 0.000%

    No Known Activations